Evaluating Trust in Multi-Agents System Through Temporal Difference Leaning.
Rishwaraj GengarajooS. G. PonnambalamChu Kiong LooPublished in: ICIRA (1) (2016)
Keyphrases
- temporal difference
- reinforcement learning
- td learning
- multi agent
- function approximation
- evaluation function
- model free
- monte carlo
- reinforcement learning algorithms
- temporal difference learning
- step size
- action selection
- actor critic
- policy evaluation
- policy iteration
- temporal difference methods
- supervised learning
- function approximators
- decision making
- state space
- active learning
- support vector
- multiscale
- learning algorithm
- predictive state representations
- data mining